Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3232 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0557. Min Act: -0.0002

Data Index: 876677 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1289810 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0449. Min Act: -0.0003

Data Index: 461495 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0471. Min Act: -0.0002

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1229354 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1142464 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0458. Min Act: -0.0002

Data Index: 738115 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0443. Min Act: -0.0003

Data Index: 448499 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1631451 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0389. Min Act: -0.0002

Data Index: 308157 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1164364 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0440. Min Act: -0.0002

Data Index: 109140 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0410. Min Act: -0.0002

Data Index: 256445 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0415. Min Act: -0.0003

Data Index: 843639 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1122614 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1022547 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0345. Min Act: -0.0003

Data Index: 551392 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1395819 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0402. Min Act: -0.0003

Data Index: 1038512 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0416. Min Act: -0.0003

Data Index: 426328 (C4 (Web Text))

Max Activating Token Index: 623